MCP Numpy vs Markdownify MCP
A side-by-side look at the MCP Numpy and Markdownify MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose MCP Numpy for data science tools work as a local process; choose Markdownify MCP for data science tools. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose MCP Numpy when
- You need dedicated capabilities in the Data Science Tools domain.
- You prefer a local stdio subprocess transport.
- You want tools like
np_array, np_zeros, np_ones.
Choose Markdownify MCP when
- You need dedicated capabilities in the Data Science Tools domain.
- Its auth model fits you: No auth required.
- You have the keys it needs:
MARKITDOWN_PATH, REPOMIX_PATH, MD_ALLOWED_PATHS, MD_SHARE_DIR. - You want tools like
youtube-to-markdown, pdf-to-markdown, bing-search-to-markdown.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Data Science Tools | Data Science Tools |
| Quality signal | 51/100 · Good | 56/100 · Good |
| Install command | Confirmed | Not confirmed yet |
| Transport | Local subprocess (stdio) | — |
| Auth | Not declared | No auth required |
| Pricing | Not declared | Free |
| Required env vars | None listed | MARKITDOWN_PATHREPOMIX_PATHMD_ALLOWED_PATHSMD_SHARE_DIR |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 2,996 |
| Directory activity | 2 views 0 installs 0 upvotes | 4 views 0 installs 0 upvotes |
| Tools | 72 | 10 |
| Full listing | View MCP Numpy | View Markdownify MCP |
Tools & capabilities
MCP Numpy tools 72
np_arrayCreate a NumPy array from a list.np_zerosCreate an array of zeros.np_onesCreate an array of ones.np_fullCreate an array filled with a constant value.np_arangeCreate an array with evenly spaced values within a given interval.np_linspaceCreate an array with evenly spaced numbers over a specified interval.np_eyeReturn a 2D identity array.np_diagCreate a diagonal array or extract the diagonal of an array.np_reshapeGive a new shape to an array without changing its data.np_transposeReverse or permute the axes of an array.np_concatenateJoin a sequence of arrays along an existing axis.np_splitSplit an array into multiple sub-arrays.- +60 more on the listing page
Markdownify MCP tools 10
youtube-to-markdownConvert YouTube videos to Markdownpdf-to-markdownConvert PDF files to Markdownbing-search-to-markdownConvert Bing search results to Markdownwebpage-to-markdownConvert web pages to Markdownimage-to-markdownConvert images to Markdown with metadataaudio-to-markdownConvert audio files to Markdown with transcriptiondocx-to-markdownConvert DOCX files to Markdownxlsx-to-markdownConvert XLSX files to Markdownpptx-to-markdownConvert PPTX files to Markdownget-markdown-fileRetrieve an existing Markdown file. File extension must end with: *.md, *.markdown.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
MCP Numpy
{
"mcpServers": {
"mcp-numpy": {
"command": "uvx",
"args": [
"mcp-numpy"
]
}
}
}
Markdownify MCP
No confirmed install command for Markdownify MCP yet — follow the setup steps linked from its listing page rather than a guessed package name.
Frequently asked questions
MCP Numpy is categorized under Data Science Tools and uses a local stdio subprocess. Markdownify MCP belongs to Data Science Tools and uses an install path we have not confirmed yet. Pick MCP Numpy for data science tools work and Markdownify MCP for data science tools.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client. Markdownify MCP has no confirmed install command yet — follow its own setup instructions.
MCP Numpy has no declared pricing — check the project's own site. Markdownify MCP is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add mcp-numpy and zcaceres-markdownify-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, MCP Numpy has a quality signal of 51/100 (Good) with 2 views, 0 installs and 0 GitHub stars. Markdownify MCP has 56/100 (Good) with 4 views, 0 installs and 2,996 GitHub stars.